Slashdot Mirror
IBM Runs 41,000 Copies of Linux on Mainframe
An anonymous reader wrote in to send us a story from Bloomberg about IBM making mainframes act like hundreds of servers. The best part is the bit at the end where they mention testing it by running
41,000 copies of Linux. "
I love it when people who know nothing about mainframes make comments like this. That's the beautiful thing about slashdot -- you can be an idiot without much effort.
Now picture all of those individual boxes being a single mainframe. Each customer would still have the security of having their own box, installing their custom software in a custom configuration, but all of the boxes would be virtual. From a customer's perspective, things would still be the same; remote login, no problems with other users overrunning their stuff (it's their individual machine), etc. The ISP only has to maintain a single machine; the mainframe.
Also, need to install another box? Just create another VM. Of course this may only scale to 41,000 boxes, but after that you just buy another mainframe and a few mainframes take much less space, power, etc, than thousands of PCesque boxes.
Jason
I think this was best described as a man bites dog story. Mainframes are great, Linux is great.
a mes)/000327CEEA?OpenDocument&~f
f m
Linux on IBM hardware is great but the real value is the contributions IBM's OS architects are making to Linux.
IBM's AIX is the best Unix. Read for yourself.
http://www.computerworld.com/home/print.nsf/(fr
http://www.dhbrown.com/dhbrown/opsysscorecard.c
More importantly IBM is taking their expertise with scalability, reliability, maintainability and adding major functionality to Linux. Such as their addition of a Journal Filing System.
In a couple years IBM will have thousands of developers servicing Linux, developing code, and architecting critical missing pieces that Linux needs to mature.
A couple mainframes running Linux is just a nice story compared to the real contribution IBM is making.
>Now that I'm browsing at +2, I do avoid a lot of junk, but I sorta miss seeing my own post
The post that was the parent's parent is rated -1:
[This is why solaris/irix are dead. (Score:-1, Flamebait)]
Well, how the heck did you see that post? And for that matter if you find a -1 discussion interesting/annoying enough to comment on, how can you trust the moderation at slashdot enough to surf at 2?
REUNITE GONDWANALAND! :)
WWJD? JWRTFM!!!
A script kiddie with one of those could DDoS himself! :)
WWJD? JWRTFM!!!
Scratch any bank, insurance company, car manufacturer, etc. etc. in the United States, and you will find a whole passle of mainframes doing all the heavy lifting.
Mainframes are far from dead. Most big business relies on them.
*sigh* If only we could kill COBOL...
*ABEND*
Want to learn about race cars? Read my Book
Maybe on the Intel front... But then Sun never really put much stock in x86 Solaris. I wouldn't use x86 Solaris unless it was the last choice - I'd run Linux for that. Get a cheap Sparc and run Solaris on that.
This probably would be a textbook example of a "well-behaved" monopoly... remember.. monopoly's can be good for consumers, it just usually happens that they aren't.
one would think that IBM learned their lesson on what it means to be a "poor behaved" monopoly.
-Stu
I'm pretty sure they've managed to port Apache natively to OS/390 itself.
-- I'm the root of all that's evil, but you can call me cookie..
The issue of running applications that take advantage of 'divvying' the work between different machines would be a moot point, really.
You see, if I wanted an applicaiton to do that, instead of running 64 copies of an OS, talking via MPI or the such, I'd run one that could divvy out the work to 64 to 128 threads, running one machine.
Granted, though, more distributed applications are available for Linux and the such then OS/390. That along could make it worth it. It wouldn;t be a 'performance' boost over running one that can thread properly in an OS/390 environment.
-- I'm the root of all that's evil, but you can call me cookie..
Nope, it's not the fact that thousands of 'processes' flooding the machines as it is thousands of places to flood the network. 41,000 behind 1 T1 line won't do all that much, compared with 1,000 hooked up to 1,000 T1's.. ;-P
-- I'm the root of all that's evil, but you can call me cookie..
Same type of thing. Just never been done on a scale of 41,000 copies.. ;-P
-- I'm the root of all that's evil, but you can call me cookie..
Oh, sorry. I forgot about the natural disaster survivalability of the Compaq and Dell servers. How silly of me.. ;-P
;-P
Of *COURSE* they'd have problems with those extreme situations, but the point is, *anything* would.
At least IBM will *LOAN* you a new machine while you rebuild.
-- I'm the root of all that's evil, but you can call me cookie..
Yep, but that post hardly went to the extent of 41,000 copies.. ;-P
-- I'm the root of all that's evil, but you can call me cookie..
Perhaps the money would be an issue, but the 4 TB of disk space? No problem there.. ;-P Easy..
-- I'm the root of all that's evil, but you can call me cookie..
Mainframes themselves are hardware redundant. Quadruple redundant power supplies, along with redundent memory and disks. Did I mention redundent processors that can take over what another was working on when it went bad? There is a reason why they are so darned expensive. There is also a reason why all of the larger banks and financial instituations use them, or Stratus machines..
-- I'm the root of all that's evil, but you can call me cookie..
I know of the isues that you raise. I assume, though, that the OS is going to be out of the way.
From what I have read about the virtual machines is that you can assign an amount of memory and processors to each VM.
If there is a good multi-threaded linux renderer,
and it can support 4+ procs well, then the OS
overhead is lower than it is for a single proc machine. The more procs per job, the faster the render. The biggest issue is where the fall off is for multiple procs.
Assuming that one of the virtual machines is a file server, then the data can be sent to the render processes at a greater speed than over a fiber conection. Every little speed up makes a difference.
Also, how the render jobs are divided up can make a big difference on what performance gains that can be made. The way that we divide shots on our render farm is good for quicker shot speed and lower frame speed. This works well for several machines with single or dual proc configs.
With a mainframe render farm, and 10+ procs a VM, then the frame speed can be increased as well. Memory requirements lessen because of shared memory and turn arround time can stay about the same.
The cost for similar horsepower from an alpha farm or an SGI Origin farm would be much higher, I assume.
-I just work here... how am I supposed to know?
Just exploit relativistic length contraction by having them run in at c * sqrt(1 - ((4.1e4)/(R *P))**2) meters per second.
where
c is the speed of light
R is the length of the room
P is the length of a penguin
"Some people have told me they don't think a fat penguin really embodies the grace of Linux, which just tells me they have never seen a angry penguin charging at them in excess of 100mph. They'd be a lot more careful about what they say if they had."
-- Linus Torvalds
"Some people have told me they don't think 41,000 penguins can fit into a single room, which just tells me they have never seen 41,000 penguins charging past them at relativistic speeds. They'd be a lot more careful about what they say if they had."
-- me
That should be:
c * sqrt(1 - ((R/ (4.1e4 * P)) ** )2) meters per second.
Anonymous, my ASS. i submitted a similary article when the FIRST story on this came out. jesus h. kriste.
-l
(ok, it's been a long day)
Help cure AIDS, cancer, and more. Donate your unused computer time to worldcommunitygrid.org. Join Team Slashdot!
I do it that way when referring to the cluster rather than the epic poem 'cause that's the way I've seen it (the cluster, not the epic poem). I figure it's probably some copyright/trademark thing, like "Krazy Glue".
I see even classic Slashdot is now pretty much unusable on dial up anymore.
The above is not redundant just because it said "beowolf cluster" and should have been moderated as funny or not moderated at all.
If you really don't get the joke, e-mail me and I'll explain it to you.
I see even classic Slashdot is now pretty much unusable on dial up anymore.
Wow, you can run 1001 copies of Linux? Cool.
Search first, ask questions later.
each one of mini-servers has the same resources and processing power.. the degredation is so small its almost non-existant.. at least it is with a mainframe running VM.. so each of those servers is essentially one machine
----
yeh.. thats the one i was thinking of when i posted.. couldnt remember who posted it or the name of it though...
----
Get Extreme Linux runing and have a virtual BEOWULF cluster.
We could have the worlds slowest supercomputer!
WOO!
-=Bob
How about 41,000 MOSIX patched Linux instances. That would make the migration of processes to idle VMs transparent.
[off topic - Is the architecture of a mainframe expensive or just the high end IBM implementation that's expensive? Could an amature cobble together a slow "mainframe" (robust, multi-cpu, multi-partition, hot swappable peripherals) at home out of PC parts and a soldering iron (ignoring the O/S issues for now)?]
Joe Batt Solid Design
Do you honestly think IBM doesn't have redudant power supplies in their AS/400s? The circuit where the power comes into the system (the power supplies all merge at this circuit) broke.
we had an as/400 at the last place I worked. It was so redundant you could change any of the cards without even turning it off. One day however, the main power line (the one all the redundant power supplies feeds into) broke and it turned itself off. IBM of course was on the case within an hour, but something like this happening with the senerio of 41000 servers would be catastrophic, and yes there are single points of failure in everything.
I am still very impressed with this technology and I hope to someday be installing new servers on mainframes =o)
kudo's IBM
Ok, Linux runs on more than three platforms (not as many as NetBSD but no need to bend the truth). How about MIPS, ARM, SPARC, Alpha, PowerPC, M68K, i386(and compats) and on a wide range of hardware in these processor groups (NetBSD does not support 25 different processer arch just 25 different hardware arch although there are a few that Linux doesn't have like ns32k, sh3/4, vax)
-- Remember: Wherever you go, there you are!
Problem with that is, something that takes down one service takes down both of them. I realize mainframes are pretty damn reliable boxes, but if it goes down, do you want it to take your webserver with it?
Sure - with uptimes measured in decades - I have no problem with that.
<I>One machine fails, 41,000 web servers</I>
Mainframe parts fail from time to time, the point is that the machine keeps running, only with a few % drop in speed until you replace the broken part. There is no crash - never. Only slight performance hits from time to time. The machine doesn't rely on everything working simultaneously, and you replace parts while running. No poweroff, no reboot, the new part is recognised instantly as you insert it.
Throughput that will blow your hair off
Ah. So that's why computer guys in bad movies are bald...
Whoa! Can you imagine what kind of a 'l33t Beowulf cluster you could do with this? I mean, you wouldn't even have to have seperate boxes! You could just run 'em all on the same machine!
</comment>
linux is the proven enterprise leader in scalability,
Not by a long shot.
security
Fair enough, although OpenBSD is better.
and reliability.
That's debateable. The OS is solid code, but what about hardware failures? Linux doesn't currently offer much in the way of single-system high availability. The only high-availability Linux offers is what I heard Linus Torvalds refer to as "cheezy high availability".
Don't get me wrong, I run Linux and love it. (My primary motivation is the GPL, actually.) But calling it the "proven enterprise leader" seems a little premature when it still has so much room for improvement. When you say "enterprise", I think terabyte-sized databases, and that's definitely not a space that Linux can play in today. It's getting there, it's the future that I'm betting on, but let's not jump the gun.
That's why big companies have multiple sites with redundancy. As much as you put them down, mainframers have been around for a very long time, and have learned how to run real mission critical applications. Of course, a single complex can be destroyed. But short of actual physical destruction, the mainframes are pretty much unstoppable.
-- Error: Cannot find file REALITY.SYS - Universe halted, please reboot!
If YOU were running one big site, maybe not. But what about if you are hosting multiple sites? You could give each customer a virtual server on which they can do whatever they want, and won't be able to access/damage anyone else.
-- Error: Cannot find file REALITY.SYS - Universe halted, please reboot!
Excuse me while I stop giggling.
Ask any big business what they run their big batch jobs on. Most of them will say mainframes.
-- Error: Cannot find file REALITY.SYS - Universe halted, please reboot!
...SABRE, the largest airline reservation service in the universe, runs on multiple Sun E10Ks
Uh, no.
Sabre's Travelocity runs on multiple Sun 10,000's. It get's its goodies from the Sabre reservation system which is multiple mainframes connected to several hundred high-end storage devices through lots of DASD controllers.
Having worked in the underground bunker, I can assure you that you can't even comprehend the volume of big iron that's down there. See the website at http://www.sabre.com/about/overview.html where they have this quote. "Our Tulsa Data Center consists of 30 mainframe computers with a capacity of 12,253 MIPs and over 60 terabytes of electronic storage - equivalent to over 15 billion pages of information."
You never really know how close to the edge you can go until you fall off.
You could have a 41,000 node cluster on just one computer!
or not...
Yes, I did read the article.
What's your point?
I answered someone's question, as to the relevance of mainframes in today's computing world.
Oh, you don't by any chance have 'reparent highly scored articles' on, do you? Is there a chance you missed the question I replied to, and saw my post as a root-level post?
Anyways, I maintain that my post was not only on topic, but factually correct.
You must be smoking crack.
In terms of modern hardware that is produced -today- (not 10 year old garbage like VAX or decstations) Linux supports at least as much as NetBSD.
The NetBSD for sparc64 is still in betas while the Linux port has been running on a wide range of ultra sparcs for a while now.
Linux also runs on SGI/MIPS, other mips, Alphas, ARM, PowerPC, M68K, and probably others (see www.linuxdoc.org for details).
Also linux, supports SMP on almost all platforams while NetBSD does do it not even on intel.
In which way NetBsd is more "industrial strength" that Linux (don't tell me about being "realy unix" and other crap).
Talk about Solaris, AIX, etc if you talk about "industrial strength". NetBSD runs only on sigle processor boxes right now, this is it.
Just how big a UPS do you have, to be able to run indefinitely until power comes back?
A: With a straw!
or:
A: Doritos.
go through the past stories here on /. . A few weeks ago there was a link to a story written by a guy who actually DID what IBM is talking about on a server where he works. And the number of Linux systems he was running on ONE of 8 processors in the mainframe was just OVER 41,000. IBM's not lieing.
~Donald / Just RTFM
You don't. You put ONE in the room...with a bunch of Mirrors!
ouch...
~Donald / Just RTFM
a shotgun against a mainframe? that's like fireing a shotgun at an aircraft carrier. you could probably put 20 rounds in some of the mid-sized ones and STILL not bring it down...
~Donald / Just RTFM
Yes, I've heard of it. What is your point?
Try to log onto the same box as three different users at the same time. Even try to have drive X: point to three different network shares at the same time.
when I was working for the state of AK(deparment of transportation, HQ in Juneau) It took lots of screaming and yelling, but it eventually happend. Usually a contractor that had less technical knowledge than myself(16 year old intern) ;->
Incidently at the same job we had an old AIX box that was running micro channel and a 68K processor at like 12 MHZ, and the thing was still the main web server for the DOT, it never crashed and the only time we shut down was when we lost power for over an hour(they were to cheap to buy a really good UPS). But somebody decided to replace it with a new machine, and the dumped somthing around 30k on it, and it had more problems that I care to rember, infact somehow we managed to f up the boot code in the prom
Single point of failure, true, but a single point of failure with redundant EVERYTHING, and recorded uptimes over 2 decades.
a bit for thought
I don't mean to troll or anything, but this is really old news, In the previous slashdot thread about Linux running on mainframe, The guy mentioned this, so why is this news all of a sudden? I am extremly disappointed that the guys handling the post, just post without checking if it is old news or reading the entire article. I am sure if CommandTaco had read the previous article, he will know that this is not news. Anyway, no troll intended. I just got very frustrated and shit I am trying to solve, so I come on slashdot to find new news to fresh my mind, thus I hope you feel my pain.
------ Curiosity killed the cat. {satisfaction brought it back | it didn't die ignorant | lack of it is killing mankind
Well, the new mainframes have really taken back a good chunck of the market, and are especially good for the ultra-high transaction areas (think financial companies). Mainframes value I/O performance above number crunching, and that is what's important for certain apps. You wouldn't want to run Quake 3 on it, but on the other hand, you aren't going to notice a lot of slow-down with heavy loads, either...
;-)
That and all these linux instances are mostly idle... unless it was 41k instances of RC5
"It's tough to be bilingual when you get hit in the head."
Darn it.... The article isn't on Bloomberg anymore... At least I can't see it!!!
greg, REMEMBER ED CURRY!!!
I think they're running 41,000 Linux instances on the mainframe to practice for the Code Wars competition ... capture the flag!
Will in Seattle
Or ditch NT and run VMS on Alpha's. Now you're talking REAL clusters.
What's my Karma Mr. Burns? "Excellent"
Anyone know what the size of this mo-chine is? I could run maybe 10-20 images of something on ours, but 41K would be pressing it!
Esa
Sorry to continue this offtopic thread but what about:
10 PRINT "THIS IS MY SIG... ";:POKE 23692,0:GOTO 10
(for all those old spectrum basic programmers whose memories are just a little bit too good)
-- MartinG To mail me: echo kewyjlcxyzvjfxbqwh | tr bcefhjklqvwxyz
If I'm not mistaken, the mainframes have the ability to run that many individual copies of linux, completely separate from each other.
For instance, if grits.example.com, meept.example.com, and beowulf.example.com were all running off of the same mainframe, each would have it's own linux. Take down the MEEPT machine, no problems for grits and beowulf, they should keep on ticking. More than virtual hosting, this would be (in theory) the same as having 41 thousand different machines running webservers.
Can you say "single point of failure"? Good! I knew you could!
Nope not halucinating. Here's the link posted on slashdot one month ago:
http://www.linuxplanet.com/l inuxplanet/reports/1532/1/
Page 4 of the article also references the guy at Dimension. Sounds like some marketing guy at IBM decided that they need to put it back into the spotlight with the IBM marketing machine behind it.
that's WOPR :P
--
linuxisgood:~$ man woman
Restating the obvious since nineteen aught five.
TRUTH OF THE MATTER : IBM originally support SNA before TCP/IP was widely in use so when IBM finally got around to implementing TCP/IP on the mainframe (around 1996) they did a shitty job (they didn't even include function prototypes in the header files) and they charged for it. It ran poorly and many of the functions were not syntacly correct. Since then however, they have complete rehauled the TCP/IP stack, corrected their implementation to match all standards and TCP/IP is an integrated part of the OS390.
As for talking SNA to an ip farm, having supported and coded to both TCP/IP and SNA, with OS390 OpenEdition - TCP/IP is by all means the way to go. As per usage of the mainframe, trust me there are plenty.
All of the above information I hold to be true from personal experience.
quick, copyright that before you see it during the next superbowl....
---- I made the Kessel Run in under 11 parsecs.
Yes on these 300 systems we have every version of Slackware, these 300 we have RedHat 2.3 through 6.0, these 400 have various builds of Debian.. :)
Would be kind of cool, you could see how each has improved, or 'suckified' as the case may be.
"Imagination is the only weapon in the war against reality." -Jules de Gautier
Squeeze out all the juices...crush into a cube and then place neatly on top of the proceeding one.
Nicely stackable..
:)
"Imagination is the only weapon in the war against reality." -Jules de Gautier
Well, it did, something to do with 40 000 velociraptors been compared to 40 000 unique linux machines running on a "dinosaur".
"Don't mind me cutting myself on Occam's Razor"
While I think its awesome that IBM is trying to run linux on just about anything they can find (linux on a toaster anyone?), and while it sounds cool that IBM can run 41000 copies of linux on one box (SETI here I come) this still doesnt get around one fundamental problem. On my web servers, CPU usage is never a problem. What always nips me is disk IO. I dont know a whole lot about the big iron, but I cant imagine them being able to skate this problem any better then my Sun webservers do. What I really would like to see IBM working on is that sexy hard drive technology, I want, no NEED a 700 gig HD for $110 for my MP3's. Not to mention that with 41000 copies of linux, INIT better be packing buck shot.
Jason
...and the geek shall inherit the earth...
www.linux-skunkworks.com
Taxpayer money?? jools, you should lay off the crack man! Or start paying attention!! IBM did their very own port to 370/390!!! Uncle Sam had less to do with it than the janitor at Parsippany!
.sig: Now legally binding!
That was what was going through my head when I saw the headline. Does it run 41000 instances of Linux REALLY REALLY SLOWLY, or do you get good performance from it?
I think that most large businesses that have been around awhile have some mainframes, but enterprise class/datacenter systems have gotten to the point that they're taking over the mainframe spots. Kind of like what the PC did to the "minicomputer".
I visited the Japan webserver for the Internet World Expo at Keio University outside Tokyo once, this was maybe three years ago. It was possibly the first time such a piece of iron was used as web server and it hauled ass. (Don't remember the stats though).
It was an SP2 (I think they had two towers actually) with storage on Auspex I believe. It was the apparently the only server that had the capacity to be backup web server for the Atlanta Olympics, also SP2 I think. I remember at the time checking out how a similar machine was being used for 3d graphics in Hawaii at the supercomputer center there to see if we could do realtime rendering for the expo.. but like lots of great things (like the phone monopoly providing 45Mbps lines all over the place for free over the year) much of what could have been done got wasted feeding rapacious ad agencies. I remember Dai Nippon tried to make money off their position of being the coordinator chosen by the government, to sell *web site space* to clients. Don't know where the disks were but probably in the same room now that I think about it. Hauled ass though!
Now if only that thing had been running a couple dozen kilolinuxes (klix? kl? KL!) we'd have taken over the country..
The "If one of those bottles should happen to fall" is from people who didn't like the line "take one down and pass it around" but couldn't hide the fact that they were beer bottles without killing the entire (relatively unkillable) song. So they watered it down
Shut one down,
Fork off another,
41000 bottles of penguin soup on the wall.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
I think this is the kind of story for a site like linuxtoday. This story hasn't changed very at all since the last time it was run (Tuesday). It's just a different news agency reporting it.
There was one web hosting company I heard abou that mentioned having full automatic generator power backup, fire supression, and such.
Slashdot social engineering at it's finest
Looks like the link is out of date--I can't find the article. Anyone have it mirrored?
41,000 Linux Kernels running - how about putting them in a Beowulf cluster? :-)
Then you would have something nearly as powerful as big mainframe, wait... er, forget about that one.
${YEAR+1} is going to be the year of Linux on the desktop!
Redundancy is best done with physical rather than logical devices. I will sleep much better knowing I have multiple boxes, running multiple raid controllers and multiple physical disks than one bug ultraserver with many OS'es.
Basically, I think the whole Sun v. IBM thing comes down to the person who makes decisions for the shop. I worked in a place where the Operations manager was refered to by saying, "If you cut him he'll bleed blue." If I am making the decision for the shop and have great experience with Sun, that is who I will choose. If IBM is my fav, that'll be the recommendation to management.
This hardly seems more than a followup on a story CmdrTaco ran a month ago. Or maybe it's just the voices in my head.
A: Tux-O-Matic
"Lend your ear while I call you a fool" Ian Anderson
Yeah, and they all interact (intefere) with each other in just slightly different ways :)
"The romance of Silicon Valley was about money - excuse me, about changing the world, one million dollars at a time."
Visit
concerdering a windows 2000 server user licence for 10 is $1,199 from microso~t.com's site
More copies of Linux.....guess if I had billions of dollars and many man hours.....*I* could do this....maybe I *will*....got that spare P166 running NT now.....try something DIFFERENT [I am going to load FreeBSD]
Wacked-Support NT
IIRC, the story was about a guy installing linux on the company mainframe. He didn't want to push it, so he stopped at 21,000.
Does anybody know how you control the access between the different OSes running on VM and the networking hardware? Can you configure, say, 100 ethernet cards or T1 connections to handle 41,000 IP addresses?
Um sir, check your math.
SABRE is an IBM solution and it's running on S/390s
"a powerful and unexpected ally..."
though not AMAZINGLY hilarious... i just sprayed my doctor pepper.
the real shiftaling has user number 5134
Karma: -43 and DROPPING!!!
YEP. it's cool.
Wow. Ibm is pretty neat, prolly why i want to intern for them. 41000 linux copies is 39999 more than i can run, but if you gave me 2 pieces of string, a piece of gold, a flint, and two monkey assistants, i could change all that. huzzah to ibm for showing that it's not dead. -love -dennis the kid -laziness is zen
Why oh why do I still laugh when I see this? *sigh* im defective. I laugh whenever I see someone mention it. Yes go ahead tell me maybe its because im a whole lot of things. But I find humor in it and I know I shouldnt :p
Jeremy
Provided the mainframe is set up correctly (and you can bet it will be ;) the best a system cracker can hope to do is compromise an individual VM or two. To take the entire thing down, they'd need access to the system console, and if the bad guy has gained physical access to your server room, one mainframe v. 40000 PC boxes makes little difference (as he can just take an ax to the power mains....)
--WhiskeyJack
Holy cats! An interesting and articulate response.
Thanks for the info, delevant.
See Mr. Boatman, you could do it too!
Any decent web admin has seen or looked at IBM's websphere package. I think between this and the Websphere package...IBM has a good focus on where they want to go. And they are taking the Linux route. I say more power to big blue. -- Seen Pirates of Silicon Valley? Does Jobs really hate IBM that much??
What type of geek are you? No UPS? If my copy of Linux crashes, it was hardware failure...
kwsNI
They're really not super-powerful in terms of CPU, but their I/O is just ridiculously powerful -- that's why they dominate in high-transaction environments (like banking).
I have no
My take on this, however, is that this technical feat is really best for web-hosting and "box on a rack" type stuff.
This way, the hosting provider simply runs one gigantic box, rather than hundreds and hundreds of smaller boxes, each of which has their own MTBF ticking away . . .
I have no
Yes, there will not be a death to the big iron. I heard it best said one time that you cannot replace a bull with 10,000 chickens. Mainframes have always had a purpose, and always will. I doubt, though, that the mainframe world will jump on the bandwagon of running linux.
Sean W. Ellis, CNE/ASE, unix luser
hahaha
The Kruger Dunning explains most post on
Yes, I sure did! I think the glitz & glamour of getting a first post on Slashdot got the better of me. I've been beaten senseless with a carp since, and I am feeling much better now! Thanks!
Segfault
segfault@bellatlantic.net
Have you people missed the point of these systems? These are not meant to be rendering farms, nor would they do too well for the bucks on SETI. They are incredibly powerful data servers. They move things from point a to point b. They do it very well, in fact. They do not have SIMD FPUs like the AltiVec, PIII, K6-2, Athlon, etc. If you want a super fast Seti machine, get an Alpha cluster. The idea of each linux instance adding speed is because of the way the data pipeline works, not some voodoo in the processor.
WARNING: there is a trojan on your
"At the end of the journey, all men think that their youth was Arcadia..." -Goethe
- Where's my karma?
- On the parking lot son!
$HOME is where the
-- silver_p
1) Get an IBM Mainframe
2) Run several Linux VMs
3) Install VMWare on every Linux VM
4) Run NT in a window on Linux VM
Piece of cake.
Feed The Need[goatse.cx]
As someone not familiar with mainframes, what kind of performance can you get out of each copy of Linux when you're running 41000 copies on a single mainframe? Also, do most big businesses use mainframes? I was under the (uninformed) impression that mainframes were kind of a thing of the past.
Ok, I read the Unisys patent in you sig...Doesn't Unisys also hold the patent on the .GIF format? Shit, now I've got all this code to rewrite in preparation for the soon-to-be impending "burn all linked lists day".
cat
Isn't NT or 2K what you really want to run on one of these? I mean, think about it, you can reboot the OS without taking out the whole machine. Just a thought. Ok, maybe the mainframe could only run 5000 copies of NT or 2800 of 2K. Still, by setting up fail-over "clusters" of these virtual windows servers, you could even simulate Real World Reliability
cat
Exactly how much resources does each VM get?
Running linux 41000 times with 25mhz, 4M of ram and 100M of disk space wont do you much good as a web server. Then again I have absolutely no idea how much fits in one of these things.
The following post brought to you by the letters V, I, and M
Don't forget that the mainframe would be down for 41,000 * 5 'site minutes'.
love is just extroverted narcissism
I submitted a copy of the Verant/StarWars story 8 hours earlier (than the final cut), except whoever rejected it felt it wasn't news at the time.
Que sera, sera...
have you ever played the game? it would run like crap on WHOPER or HAL!
There are two kinds of people in the world: Those with good memory.
It will just change the way CTO will compare the length of their, oups, the size of their mainframes. While playing golf, Joe Bloe will say to John Smith:
- Hey you! My mainframe can run 1000 more copies of Linux than yours!
And John will reply:
- May be, but you aren't running the latest kernel version!
However, mainframes are still good for OLTP and they are really good to keep the IT budget high.
>Hey they tried! But each NT server tied itself >up trying to fight the others to be Domain >Controllers!
Cute. I guess you probably meant "each NT server tied itself up trying to fight the others to be be domain master browser!"
I can see that you are completely IGNORANT of mainframe technology. IBM is making tons of money on what you named LEGACY SYSTEM. Bank,Insurance,Health Care and Airline Industry to name a few. Try to run an airline reservation on a SUN....or on Linux..
I didn't find it at the link on slashot. I searched Bloomberg and found it under IBM here: http://quote.bloomberg.com/fgcgi.cgi?s=9562e335cb9 4bae8f72f85ace5b23753&T=marketsquote99_n ews.ht
Power tends to corrupt, and absolute power corrupts absolutely.
Didn't IBM create a PCI version of this at one point? Plug in the card, and you've got a -- moderately powered -- mainframe.
I could never find a price or specs on that beast, and I know it's been a couple years.
A firewall can not protect you from yourself. Turn off what you do not need. Do not use the firewall to do your work.
Get a life ...
Sorry, but that's not the truth. VM had TCP/IP support back in the early 1980s, and at heart it's the same solid code running today. The implementation was originally done for use by CSNET by Dr. Larry Landweber's group out at U. Wisconsin, and was known in those days as "WISCNET". (Yes, *THAT* Landweber.) In fact, it still recognizes the CSNET loopback address (14.0.0.1)!
Ground0 would seem to be mistaking OS/390 for VM. See jms's excellant summary post for the key differences - it's like saying Linux and Windows are the same 'cause they both run on Intel hardware.
Ross Patterson
Sterling Software (um, make that Computer Associates)
Ross Patterson
Sterling Software (um, make that Computer Associates)
Umm, this proves you know nothing about IBM's S/390 mainframe. The VM system allows a copy of the operating system to run as if it was on its own machine. Now, a guy has run 41,100 copies of Linux on the machine before running out of resources.
:-D
I would sure love to use Linux 2.4's SMP capabilities and have a 32-processor system with 64 gigs of RAM. I wonder how many copies of Linux that can run
And to annoy you once more, IT IS TRUE DAMNIT@#!
But does it run apache?A linux server is really good if it runs Apache.
The penguins have revolted...Visit The UPGR
------------------------
Thus Spake ComradePenguin
If I were going to run a big web site with a mainframe, why would I want to subdivide it into multiple mini-servers? I'm thrilled the iron giants can run Linux, and if I need their processing power, I'd just run a single copy of it.
Is the point that ISPs can consolidate all of their servers into a few mainframes? Couldn't they have done that before, without subdividing the mainframe?
say radius server
and it went down
it would be incredibly easy to bring one of the 41000 others up to replace it??
In this case it seems like a pretty good idea.
I think this shows a giant leap in the progression of how computers will fit into our lives, but I am not sure that this is the best approach. If we could work more on an operating system that could multitask far beyond the current OSs, then we would not have to use the extra RAM and CPU cycles of running many instances of the same operating system. Also, similar programs or programs that use the same database, etc. could share resources.
With the amount of data Linux has to load in for the kernel (even before Apache, which has a huge memory overhead for all the multi-megabyte modules), you will be wasting a large proportion of the mainframe's memory.
Hate to say it, but wouldn't it be more effective to run NT? Although there are good reasons why Linux is not as scalable (lack of high-spec machines in the hands of Linux developers), which are being fixed - for now NT scales *far* better.
Adam
Alack! why do the denizens of Slashdot
Insist on the spelling of "Beowulf"
With an O as its final vowel?
Truly it pains me; those who doubt
My authority should consult
This Wednesday's New York Times.
Does my Nobel Prize naught signify?
Reading Slashdot kiddies speculate the capabilites and limitiation of mainframes like the s/390 is like listening to joe-sixpack talk about double-eww-dot-com on the subway.
I've got no problems with mainframes; I think they're pretty cool. The very fact that they did it proves their, IBM's, prowess in computing systems.
I wouldn't want to run Linux on anything less than one OS instance per processor. Such a system would make a fine Beowulf cluster due to the fact that the internal bandwidth of the mainframe is higher than an method of network wiring available today. It would be truly awesome. I know there is overhead in running multiple kernels and supporting drivers and such but it should be faster than discreet machines.
Anybody have any idea why it wouldn't work?
Codifex Maximus ~ In search of... a shorter sig.
Mainframes are usually tuned for block device I/O and are notorious for being crappy at TCP/IP. I'm not sure if this is a result of OS/390 being bad at it or the hardware, but my impression is that mainframes do best talking SNA to a farm of Unix boxes that act as little more than IP stacks proxying data to the mainframes.
Isn't there one of the mainframe gurus from Schwab on here? Those guys run some big iron in the back room...
Remember that what's inside of you doesn't matter because nobody can see it.
WOW that is amazing!
The Cure of the ills of Democracy is more Democracy.
Erlang Developer and podcaster
This would work well for a render farm if...
;)
There was terabytes of ram. You would want a couple hundred meg of ram for each render job.
One thing that would be better is to assign 4 procs to a machine, thus reducing the total amount of memory to be 10,000 machines X 250-500 MB.
I am sure that we could get that much memory for the system...
I don't think that most render engine would port well to 100 procs... but... if it was reprogramed with that in mind... it might do really well.
Too bad I don't have the time or the resources.
-I just work here... how am I supposed to know?
Or they could one-up EDS.
Scene:
Images of a cat happily playing around in it's own happy world.
Zoom out of cat brain and see Matrix-like techno-hive with thousands of cats on feeder tubes, with electricity sparking around.
Voice Over:
Cat herding. It's what we do.
--
"L'IT c'est moi!"
--
-- Slashdot sucks.
I'm getting a story on how Citrix isn't going to meet it's earnings estimates this quarter.
Chas - The one, the only.
THANK GOD!!!
Chas - The one, the only.
THANK GOD!!!
As someone else had suggested this opens a neat new possibility: a hire-a-server service that gives you total root access on your own linux box; each "server" is actually a prepackaged linux memory snapshot running in VM.
Just think - any script-kiddie who gets root is unable to see he has't got the machine to himself, powerless to hide from admins who can watch his every move from the real OS, and unable to do any damage that can't be rolled back in an eyeblink. Crashes and "reboots" recover in seconds. And, when the customer is done hiring their server, it just drops into the bit bucket and the resources are reallocated to other servers.
Assuming you weren't just attempting humor and need to learn quite a bit more about how mainframes work, go read this very interesting piece at linuxplanet.com about running virtual machines on mainframes and running other OS's on those virtual machines. It's several pages long but well worth the effort.
IBM's mainframe operating systems will stay right there on the mainframes.
I see even classic Slashdot is now pretty much unusable on dial up anymore.
I remember a story not too long ago, i dont remember the name.. but it was about a guy talking about running a few thousand copies of linux on a VM mainframe OS/390 or something like that... or am i just halucinating??
----
I have kinds had this conspiracy theory about IBM. I think that they see Linux, and open source, as a way to have M$ levels of power without the problems. If challenged, they could just say "Well, the code is out there, why didn't YOU think it up? Neener neener," and go back to world domination. They create nifty hardware hacks which they release - after all, they aren't of much use unless you have a mainframe to begin with (which you come to them for). They supply code to a standards-based Web server (and release that, too). Monopoly? Heck no, we gave you the source code!
Slightly off topic but its been on my mind.
ZOMG I WOULD LOVE TO KNOW ABOUT YOUR FEELINGS ON MACINTOSH VERSUS WINDOWS, VI VERSUS EMACS, AND HOW YOU'RE NOT A DORK
Could we rewrite Apache to spawn off a new copy of the operating system for each connection?
(this joke is kind of obvious, so forgive me if someone else has already posted it)
Scuttlemonkey is a troll
God, I spent weeks studying that instruction, trying to figure out how to out it to work. IBM put out an entire BOOK on that instruction. It's basically a huge chunk of microcode that emulates a small piece of the VM kernel. It's pretty much useless for hacking/play purposes, unless you want to design around the instruction.
:)
I had better luck playing with the vector instructions. I had a very fast fractal generator
Right. VM has shared memory across virtual machines. Even though there are 41,400 images of Linux, there need be only one copy of the code in storage, shared by all of those virtual machines.
If one of those virtual machines were to attempt to write to a memory page, CP would simply fork off a private copy of that page, and continue on.
I believe that Linux (and most unixes) do the same thing -- one read-only copy for each currently running executable, shared between all processes running that executable.
Another reason to run a cluster within a single machine is to circumvent bottlenecks within Linux. If you have an application that insists on forking off dozens and dozens of tasks, you will start to run into the Linux scheduling algorithms, which are performance-optimized for a small number of tasks.
If you create multiple Linux images using the zero-latency networking capabilities that VM gives you, you can split up your application until there are a small enough number of tasks per Linux image to run smoothly.
Another good reason is, as AC says, if some users need root access for some reason. You can set up a system as a virtual machine, give them root access to that image, and nothing they can do will affect any other virtual machine in the system. Great for testing new Linux kernels. In fact, VM was designed specifically for this purpose -- except that it was used to debug new OS/390 (MVS) kernels instead.
Referring to your OT question, a few months ago I ran across a research project on this. In a nutshell, they are building a mainframe-like computer out of the reject commodity parts from the manufacturing plants.
On first boot the OS goes through and checks each chip/component piece by piece for reliability. If unreliable, it tries to assess exactly how/where it is unreliable and routes around the problems. The first boot and diagnose process takes about a week!
The end result is very reliable large computer (64 CPUs, IIRC) with awesome failover capabilities (since dealing with broken hardware is integral to the whole system). I don't remember the figures, but it was something like the final running computer might have %30 or 40% broken parts.
Oh and don't forget the bit about 'commodity parts' - broken cheap IBM clone hardware.
I'm sorry I can't give you a link, I'm not at home and my net connection is too slow/unreliable for search for it. However, the project is funded at least in part by HP and it is hosted at a university (Sanford? Cornell?).
They do have a working prototype, though which definition of "working" they are using... I'm in no position do judge. Cool pictures though. Cool project too.
cheers,
-matt
I can't believe i'm the first to suggest this, but i'd like to see IBM run 40,000 virtual machines on one server and then link them all together in a Beowulf cluster.
--
--
Mod up a post Rob doesn't like and you'll never mod again
This was posted weeks ago, no?
The article was something to do with 'notes on runing linux on a mainframe'.
They made a good point, though.
One IBM mainframe, and you could present thousands of 'virtual' linux boxen to your web clients.... virtual machines in the extreme.
You thought you could attack 1 machine from billions of places to take it down.. Now you can attack 1 machine and bring millions of servers down! (at least thousands) Worse yet, have all 41k servers attack someone else! ..well.. maybe not ;> -end of joke-
---
-
ping -f 255.255.255.255 # if only
IBM already has the fastest web server in the world in their mainframe. Why would anyone want to switch to Linux and give up on the VIPA Takeover and Sysplex technologies? This whole demonstration is just extra hype to get Linux people interested in what the mainframe hardware can do. (Which is not necessarily a bad thing)
Aah, change is good. -- Rafiki
Yeah, but it ain't easy. -- Simba
They have moved their article off of their "ticker" page. Those of you who wish to read it can find it here .
I mod down any one who says "I'm sure I will get modded down for this"
Redundant memory, redundant hard drives, redundant processors, .... But what happens when the cleaning staff unplugs it from the UPS because they needed that plug for their vacuum?
They have redundant power feeds, too. And not just the whole machine - every box in the room has 'em, and each feed powers a separate set of power supplies in the box. (Some devices get their power from their controllers. And these are generally driven by multiple controllers...)
If they did it right, the power cords go to opposite sides of the room, thence by different paths to different feed points where the building gets power from separate feeds that came in from different parts of the grid (which was a consideration in chosing the site for the computer center: at a grid boundary, or close enough that you can pay to string a line from a different section.
There's at least one UPS, of course. On ONE of those two feeds. (A UPS, on the average, creates one extra power failure in its first year of operation. B-) )
And I'd like to see the janitorial staff try to plug into the connectors that feed the mainframe. They aren't your typical duplex outlet.
The point of concurrent maintainence, of course, is that ANYTHING in the box can fail, and be swapped out and replaced, without stopping the processes.
They might not get as much CPU time or disk response speed as usual while the system is in "degraded" mode due to failed parts waiting for or undergoing replacement. But they run continuously for years - and are shooting for forever.
I hear they once moved a Tandem across town by putting in a mainframe's frame and the comm lines, then gradually installing boards in the new location and unplugging them from the old, until the whole machine was at the new site. Still running.
Try THAT with your PC. B-)
Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
JMS made some good points, but the basic advantages he suggests (better scheduler control, better memory allocation) really can be done by tweaking the process scheduler and memory allocation functions in the operating system, rather than massively cloning kernels. If there are limitations in the hardware (e.g. how many bits or frames of translation table space, etc.), this doesn't really get around it, but if you can already run more than 1 copy over VM, it may be easier than hacking everything that touches memory allocation. It can depend a lot on the sparseness of the virtual memory space you're trying to simulate.
While it may not do much for user space work, it would be a fun place to test kernels. You save the room-full of 1U rack-mounted boxes, and instead have lots of virtual machines you can blow away when your kernel hack fails, and it lets you test lots of different parameter combinations in parallel.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
Unix systems do a really good job of keeping user-space processes from trashing each other, though they occasionally hog resources in ways at which the system designers didn't expect or the sysadmins didn't pay attention to soon enough. But it's still possible to crash Unix systems by messing around too much in the kernel. Linux has gotten much better than the old days, but making changes still means testing. A Virtual Machine environment, as long as it looks close enough to the real thing, can give you a convenient environment for testing kernel hacks, drivers for non-hardware-dependent pseudo-devices, and other things that may stomp around underneath the OS's hard crunchy shell.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
I fail to see why the "best" part is that these mainframes run Linux? If they had been running a *BSD, Windows 2000, or something else, would that not be as great? Why is Linux the flavor in the soup that's touted over the other ingredients? Give me a freaking break already. Want to advertise Linux? Put up more banner ads. Want to report news? Do so with some semblence of journalistic integrity.
Some "obsolete" but workable IBM AS/400 units are sold very cheaply. I know of at least one enterprising geek who filled a basement with AS/400s that he bought with a price negotiated by the pound . They all run, what he does with them I don't know, I'd hate to see his electric bill.
(IBM Servers sold by the pound =anagram>'Short-lived!' presumed by snob.
So dry: rubbish developments.)
[almost never get any +1 when I include an anagram, I wonder why...
[
Weird, IBM used to be to Wang (and DEC and such) as Microsoft is to Linux and various Bsd's. So if the devil has been incarnated anew in Redmond, who'd have guessed that Armonk would end up hosting more than its share of the Open Source insurgency?
Ed Craig "Who cares what you think?" George W. Bush, 4th of July 2001
Last month's story had much more details.
One thing neither of them talk about. VM/370 allows shared code between "machines". If a chunk of code can be ROMable, then you can load a single read-only copy of the kernel, or EMACS, and everyone who uses it gets the same copy, exectuing out of the same chunk of RAM. I don't know if this is at all relevant in Linux. Is the executable code typically kept (widely) separate from the data?
And have to become the next Microsoft? We've already been through the DOJ grinder once, and both employees who remember it don't want to go back.
As I have explained before, IBM believes in being a player in every market and a monopolizer of none. Our strategy is to get dominance in any market we play in, if possible. If we don't have dominance, develop and/or produce cutting edge components like GPS chips, hard drives, Transmeta chips, etc. and make a few cents off of every dollar our competitor makes. If you use someone else's software or hardware, our services consultants will still fly out and tell you how to make the best of it and fix it when it breaks (like Win 2K). In short, IBM stays the biggest single IT company in the world without holding a monopoly club over any given market. It enables those of us who work for Big Blue to feel like the good guys, especially when IBM is amongst the leaders in the push for standards that are non-MS-centric for such efforts as Java, etc.
Disclaimer: I don't "represent" IBM. I just work there.
B. Elgin
B. Elgin
"Read at your own risk; feel free to ignore."
Here's why:
IBM actually manufactures (and sells) a mainframe system that comes with it's OWN satellite uplink and guaranteed bandwidth. They're designed for use on oil platforms.
These systems also come with some insanely fancy remote-mirroring and update functions (because, after all, oil platforms are hostile environments for most computers).
So, if you're worried about natural disasters, you could theoretically buy two of these systems. Then you won't need to worry about anything less than a nuclear war -- even if the land-lines get killed, you've still got your friendly satellite.
Besides which, distributing a couple o' mainframes is a hell of a lot easier than effectively distributing 82,000 PC-based systems! I mean, heck, just think of the POWER requirements for the PC equivalents . . . Good lord, you'd probably have components failing on at least one machine every five minutes or so (MTBF would kill ya on that many machines).
Of course, I could be wrong.
I have no
At last, all those old servers can finally run a nice OS :o) Now, who wants a second-hand mainframe?
ManicHawk - Just because you're manic doesn't mean the walls aren't bouncy
A: Use a blender!
Sorry if it's a little, umm, inflamatory...
It would seem to be an excelent way to set up multi homed web servers.
One organization could lease space and a linux install to anyone.
This would help all those who have put boxes at a distant local just for the use of bandwidth etc.
99.999 % track record.
For those who don't do the math, that's an average of a 5 minutes of down time *PER YEAR*
If the problems that you forsee *DO* happen, and it goes down for, oh, and hour, that would statistically speaking mean that 12 other sites had 0% down time for the year.
The cumulative down times of 41,000 servers would be *MUCH* more then 5 minutes.
Now, 41,000 is a *GROSS* exageration.
-- I'm the root of all that's evil, but you can call me cookie..
Problem with that is, something that takes down one service takes down both of them. I realize mainframes are pretty damn reliable boxes, but if it goes down, do you want it to take your webserver with it?
Not quite. The S/390 runs multiple OSs is LPARs (Logical Partitions) and they are pretty much independent of each other. The webserver can run on linux (or OE, the mainframe port of AIX) and not affect a production LPAR running OS/390 at all.
Finkployd (Systems Programmer at PSU)
But I bet Ultima IX still runs like crap on it.
DrLunch.com The site that tells you what's for lunch!
Remember that mainframes (i.e. 390) have some really nice kill and redundancy features... processor or memory stick dies... oh well, shut it down and keep going, then fire off an alert to the admin. Concurrent matainance.... mmmm....
"It's tough to be bilingual when you get hit in the head."
I must say, Linuxworld proves to be much more interesting than /. as for posted newslinks. (but the discussion on /. is more interesting).
:o)
But on topic: I had the pleasure to work with VM/ESA on top of which was running another IBM Mainframe OS, VSE/ESA. Several coipes of VSE were runnning at any time. And we of course started additional ones, for testing of programs. And the uptime was incredible!!! We had an entire disk unit *destroyed* (filings of the hard disk material flying around), but the system was still happily humming on. Very impressive.
Also, did you guys know that OS/2 was developed partly by running it on top of VM? I think these mainframes + VM are the coolest technology to come out of IBM, if we don't count the bionic chip coming out in 2015
Sigged!
Microsoft doesn't try other platforms for WinNT.
Microsoft works out a license arrangement, and the hardware vendor does the porting code of the very few bits of native code.
It's the hardware vendors who have given up on their own WinNT ports... MIPS and DEC.
The only hardware Microsoft has been interested in, is the hardware which the typical end-user would put their grubby mitts on. First, Apple BASIC cards (when every end-user knew what a PCB was). Then mice. A short-lived i186 booster card. Millions of more mice. Trackball. More mice. A few gaming devices. More mice. Now the X-Box. Common thread: grubby mitts of the unwashed masses.
I'm not flamebaiting here. Linux may be cool, Linux may have superior traits in some regards, but as a whole, Linux has a lot to learn about offering products to the winning markets. 'Cuz there's only two winning markets: business-to-business (Why should I trust you with my billion-dollar mission-critical apps? You don't even have the money to pay for software!*) and mass-market (I don't even know how to turn the dang thing on!**)
* Suits don't care about how kewl something is. They don't want to be surprised. They don't want risk. They want to do it just like the other guy does it, except with a somehow better profit margin.
** If you say you've never heard someone say this exact line, you're lying.
[
"Dimension, a Herndon, Virginia-based computer consultant that Nortel Networks Corp. agreed to buy last month, tested 41,000 copies of Linux for a large telecommunications customer. The client, which Dimension wouldn't name, provides Internet access."
Hmm, Qwest just annouced they were entering into a hosting partnership with IBM. Opening many joint-venture web hosting centres in the US...
At the same time IBM also has a deal with a web site design firm in Minneapolis MN to make a large ammounts of web sites...
The plot thickens as they attempt to take over the world!
From the article, I got the impression that they wanted customers to use their existing mainframes (presumably data warehouses and such) as webservers. At least, that's what I got out of their claims at increasing speed by doing away with webserver-database latency.
Problem with that is, something that takes down one service takes down both of them. I realize mainframes are pretty damn reliable boxes, but if it goes down, do you want it to take your webserver with it?
(I'm assuming the security issues inherent in putting a webserver -- esp. a public one -- directly on one's data warehouse have been hashed out in the course of the VM development. Nonetheless, websites are flypaper for h4x0rz -- that's putting a lot of trust in software.)
Same thing holds for anyone using it to replace 41,000 (yeah, whatever) webservers. One machine fails, 41,000 web servers (and god knows how many sites) out of business. I suppose a redundant mainframe is sufficient insurance -- but how much more appealing is that than buying a comparable number of Suns, and having just a few backup boxes?
Seems like an interesting idea, and it certainly creates options. I don't know if it's the Sun-killer, though; and though it might convince existing users to not buy Sun, I don't know how many new buyers it would attract.
Then again, the closest I got to working on a mainframe was touring a server room with a bunch of AS/400's in it once, so don't think I'm the Delphic Oracle or anything. :)
phil
There are more given in the LinuxPlanet article (which is where I got the other links).
Seems to me that if I had a mainframe, or could get hold of one, this is an awesome virtual hosting environment.
Give me money, and I give you root access to your own, incredibly reliable, Linux box. If you trash it, it can be restored from backups in seconds. Incremental cost of adding another virtual host: almost nil. Until, of course, we get to 41,000. By then I should have enough money to buy a new mainframe. And so on.
--
E_NOSIG
...one copy for each distro.
*ducks*
Here's my copy of DeCSS. Where's yours?
censorship is a form of noise, which actively seeks to drown out content with silence - Crash Culligan
Hey they tried! But each NT server tied itself up trying to fight the others to be Domain Controllers!
So how do *you* fit 41,000 penguins in a room?
;-)
(sorry for the ad slogan infringement, but it seemed like the right thing to do
-Bugbbq
(to the tune of 99 bottles of beer/..... sorta)
41000 copies of Linux on the box
41000 copies of Linux
if one of those copies should happen to fail
wait in the dark, til the power comes on
(Repeat)
Finally, someone catches on to the good that big iron can do. Mainframes *DO* have a practical use in the modern computing environment. Ever time I hear someone mention the 'Old, vunerable mainframes', I cringe.
They have been doing what VMWare is doing, aka, running virtual machines, for nearly three decades. They know what they're doing.
I'd be interested to know what large ISP is looking to use them in this way. To my knowledge, this would be the first published use of the mainframes specifically to serve as a server-multiplexor (Is that a word?) in an ISP environment. This could be the 'next big thing' for these machines. Either that, or be yet another flash in the pan with alot of 'cool' factor..
(Fingers crossed)
-- I'm the root of all that's evil, but you can call me cookie..
I'm not involved in this work; I wish I was. However, I'm very familiar with VM/ESA and the low-level programming facilities that are being used to pull of this 41,000 Linux virtual machine cluster. I used to write assembly language programs that used IUCV and virtual CTCAs, and what they are doing is crystal clear.
First off, this setup is running under VM/ESA. This is NOT the same operating system as OS/390. Diehard VM'ers tend to view OS/390 about as fondly as Linux users view Windows. OS/390 is the huge, IBM-management-approved operating system with JCL, that evolved out of OS/360. VM is the back-room project that IBM management has tried to kill, over and over, but can't kill, because it's needed for OS/390 development, IBM developers demand it, and many customers demand it. OS/390 is what management wants to sell -- it's the "strategic" operating system. VM/CMS is what the IBM development teams use because it was designed, from the bottom up, by IBM's best software developers, specifically as a platform for software development. Really. I used it for 15 years. If you're developing or debugging IBM assembly code, it's just the best. VM was a skunkworks project, and a damn fine one. It's a shame that it isn't that well known.
The two operating systems should NOT be confused. Different operating systems. Entirely. OS/390 can run as a guest under VM/ESA, but not vice versa.
That said, VM has a HORRIBLE native TCP/IP implementation. It's a big program, written in Pascal, and it's a dog. In fact, it's about the weakest part of VM. It never got much attention, because mainframe networking has always been driven by SNA, VTAM, etc. and IBM development is traditionally done on a 3270 style terminal. All the tools, XEDIT, the mail system, etc, are all designed for 3270, block mode terminals. VM is lacking in TCP/IP support for the same reason that Unix systems are lacking in SNA support, because no one wanted it. This is changing.
The VM TCP/IP implementation is a standalone program. The TCP/IP program runs in its own virtual machine. When someone wants to connect to TCP/IP, they use a system call to establish a connection between their virtual machine and the TCP/IP virtual machine using a facility called IUCV -- Inter User Communication Vehicle.
IUCV is a very fast, block-oriented, secure, unspoofable point to point protocol for establishing data links between virtual machines. A programmer using IUCV starts by creating a link to the target, then sends blocked data by making a system call with the address/length of the data. The CP nucleus (their word for the kernel) copies the data into the system address space, synthesises and schedules an interrupt for the target virtual machine, and immediately reschedules the source virtual machine. The target virtual machine receives the interrupt, issues an IUCV receive system call, and CP copies the data into the target machine address space. This is all done completely asynchronously. It's extremely fast, and utterly secure. Zero-latency networking is a nice thing to have.
Which leads to something very cool. IP over IUCV.
I don't know exactly how they set their system up, but here are the basic tools that they have to work with:
1) TCP/IP to the outside world can be handled in at least two ways:
o Through a native Linux network device driver. In VM, physical peripheral devices are assigned to individual virtual machines. A virtual machine with a physical network interface attached to it simply uses it as an ordinary I/O device.
o Via a connection to a native TCP/IP virtual machine, using a special device driver that knows the native IP-via-IUCV protocol.
2) Connections between virtual Linux machines can be handled in a couple of ways:
o through a virtual (or real) CTCA (Channel to Channel adapter.) a CTCA is a high speed parallel interface used to connect mainframes together, point to point, very fast. If you use virtual CTCAs, you can move Linux images from one machine to another without having to ever reconfigure anything within the Linux images themselves simply by replacing the virtual CTCAs with an attached real CTCA and changing the directory entry of the virtual machine.
o Using an IUCV driver, one can interconnect all of the internal Linux images via virtual point-to-point lines. This is much faster then virtual CTCAs. The drawback being that you need to configure IUCV links within a virtual machine, so changing things around requires reconfiguration within the linux image itself, and IUCV is designed to work efficiently within a single system, not across multiple systems. It can be done, but it's a hack, and it's inefficient.
o Through an obsolete API called VMCF, which was superceded by IUCV.
The big innovation going on here is the realization that by running multiple Linux images on a single machine, or multiple Linux images on multiple machines, using mostly IUCV links, one can almost eliminate the network latency, because the data transfers are simply memory copies, and one can eliminate the network collision problem, and the network traffic problems. If you have 100 machines sitting on a fast ethernet, and you start getting a lot of inter-machine traffic, you are going to have collisions, and each machine has to waste a fair amount of time evaluating which packets are his. This removes the biggest bottleneck in large clusters of small machines, Also, an IUCV connection is guaranteed to never drop a packet, and always transmits packets in order, so TCP over IUCV proceeds smoothly and efficiently.
This gives you lots of scaling options for your virtual Linux network.
One more point.
There was an article that came out two days ago, but due to a slashdot bug never appeared on the main page, but proceeded directly to the "older news" catagory. In it, the author wrote:
An S/390 running a light load will not run as quickly as a fast PC server under a light load, according to Courtney. The difference between the two systems will not be apparent until the load is much larger.
"The PC will begin to degrade and will typically reach a point where it avalanches down in performance as its load limit is exceeded. The mainframe starts out at a lower performance level, from the standpoint of an individual program task, but degrades much more slowly and much more linearly as the load increases," he says.
Revisiting my previous comment in this thread, I remember, a while ago, reading in another article about a difference of opinion between some IBM programmers and the kernel maintainers. Supposedly, IBM was complaining that Linux performance went south when the number of running tasks became large, and proposed some scheduler changes, but the kernel developers didn't want to change it because the changes would have slowed the kernel down in the "normal" case of only a few active processes. Does anyone have a link to this or remember what I'm talking about?
Sounds like this article is describing the same known effect. However, by running multiple images of Linux under VM, one obtains a workaround for the problem. If a Linux virtual machine is overloaded, create a new virtual machine image, and offload one or more of the biggest processes to run on the new machine.
This is all very interesting stuff. Don't forget, the stuff we're just discovering now in the Linux world, is largely stuff that the IBMers, and especially the VMers have been working on and perfecting for about 30 years. I'd love to see a Linux kernel that can run 41,000 tasks, with a linear performance degradation curve. Until then, at least there is a way to run Linux on an operating system that has those characteristics.
And the fact that their operating system can run 41000+ simultaneous tasks without disintegrating, but ours can't, should eventually get under someone's skin and prompt efforts to make the Linux kernel scale better under heavy multitasking loads. Why should they have all the fun?
- John
They considered running NT servers, but they didn't have the $8,000,000 for the licenses and the 4 TB of disk space. :)